Search

Background: Nursing notes are among the most critical tasks for nurses, and not performing it in a correct manner will lead nurses to face numerous issues and problems. Nursing notes can be written in a variety of ways. One approach is the nursing process-based SOAPIE (Subjective, Objective, Assessment, Plan, Intervention, Evaluation) method. Thus, the present research was conducted to determine of the SOAPIE Nursing note Method on the quality of Nursing Documentation. Methods: The present semi-experimental study was conducted in 2021 at Yasuj hospitals, in Iran. The samples consisted of 120 nurses selected through the convenience sampling method based on the inclusion criteria. The samples were assigned to two intervention and control groups through a random allocation method. Nursing notes using the SOAPIE method was implemented for 3 weeks in the intervention group after obtaining informed consent. The data were collected using the checklist of nursing documentation principles, which involved two sections of demographic information and nursing documentation-related items before the intervention and one month after the intervention. The mean score of each of the eleven principles was determined from the total score of 100. Three levels were considered in the tool’s scoring: Poor (0-33), moderate (34-66), and favorable (67-100). The descriptive and inferential statistics methods (the chi-square test, independent t-test, and paired t-test) and SPSS software version 21 were used for data analysis. Results: The total score of quality of nursing documentation had no statistically significant difference in the intervention and control groups before the intervention (P

Nursing staff record observations about older people under their care in free-text nursing notes. These notes contain older people's care needs, disease symptoms, frequency of symptom occurrence, nursing actions, etc. Therefore, it is vital to develop a technique to uncover important data from these notes. This study developed and evaluated a deep learning and transfer learning-based named entity recognition (NER) model for extracting symptoms of agitation in dementia from the nursing notes. We employed a Clinical BioBERT model for word embedding. Then we applied bidirectional long-short-term memory (BiLSTM) and conditional random field (CRF) models for NER on nursing notes from Australian residential aged care facilities. The proposed NER model achieves satisfactory performance in extracting symptoms of agitation in dementia with a 75% F1 score and 78% accuracy. We will further develop machine learning models to recommend the optimal nursing actions to manage agitation. [ABSTRACT FROM AUTHOR]

[Display omitted] Malnutrition is a prevalent issue in aged care facilities (RACFs), leading to adverse health outcomes. The ability to efficiently extract key clinical information from a large volume of data in electronic health records (EHR) can improve understanding about the extent of the problem and developing effective interventions. This research aimed to test the efficacy of zero-shot prompt engineering applied to generative artificial intelligence (AI) models on their own and in combination with retrieval augmented generation (RAG), for the automating tasks of summarizing both structured and unstructured data in EHR and extracting important malnutrition information. We utilized Llama 2 13B model with zero-shot prompting. The dataset comprises unstructured and structured EHRs related to malnutrition management in 40 Australian RACFs. We employed zero-shot learning to the model alone first, then combined it with RAG to accomplish two tasks: generate structured summaries about the nutritional status of a client and extract key information about malnutrition risk factors. We utilized 25 notes in the first task and 1,399 in the second task. We evaluated the model's output of each task manually against a gold standard dataset. The evaluation outcomes indicated that zero-shot learning applied to generative AI model is highly effective in summarizing and extracting information about nutritional status of RACFs' clients. The generated summaries provided concise and accurate representation of the original data with an overall accuracy of 93.25%. The addition of RAG improved the summarization process, leading to a 6% increase and achieving an accuracy of 99.25%. The model also proved its capability in extracting risk factors with an accuracy of 90%. However, adding RAG did not further improve accuracy in this task. Overall, the model has shown a robust performance when information was explicitly stated in the notes; however, it could encounter hallucination limitations, particularly when details were not explicitly provided. This study demonstrates the high performance and limitations of applying zero-shot learning to generative AI models to automatic generation of structured summarization of EHRs data and extracting key clinical information. The inclusion of the RAG approach improved the model performance and mitigated the hallucination problem. [ABSTRACT FROM AUTHOR]

Background: Falls are common in hospitalized patients, especially in older adults. Currently, risk assessment tools lack specificity and sensitivity to be clinically useful. Recently it was discovered free text in nursing notes contains valuable information on fall risk factors. We used text mining techniques to search for any text characteristics (not only related to known risk factors) associated with falls. Methods: In this retrospective case-control pilot study, hospitalized patients aged ≥70 years who experienced a fall were included using incident reports. Controls were matched for sex, age and length of stay. Data were collected from free text in nursing notes 72 h prior to the fall and for similar hours in controls. Number of words, frequencies of single words and word combinations were calculated and compared between both groups. Results: 19 fallers and 19 non-fallers were included, with a total of 362 nursing notes. More words were used in nursing notes in fallers in total (10,523 vs 7,510, p

Abstract Background There is an urgent need to improve quality of care to reduce avoidable mortality and morbidity from surgical diseases in low- and middle-income countries. Currently, there is a lack of knowledge about how evidence-based health system strengthening interventions can be implemented effectively to improve quality of care in these settings. To address this gap, we have developed a multifaceted quality improvement intervention to improve nursing documentation in a low-income country hospital setting. The aim of this pilot project is to test the intervention within the surgical department of a national referral hospital in Freetown, Sierra Leone. Methods This project was co-developed and co-designed by in-country stakeholders and UK-based researchers, after a multiple-methodology assessment of needs (qualitative, quantitative), guided by a participatory ‘Theory of Change’ process. It has a mixed-method, quasi-experimental evaluation design underpinned by implementation and improvement science theoretical approaches. It consists of three distinct phases—(1) pre-implementation(project set up and review of hospital relevant policies and forms), (2) intervention implementation (awareness drive, training package, audit and feedback), and (3) evaluation of (a) the feasibility of delivering the intervention and capturing implementation and process outcomes, (b) the impact of implementation strategies on the adoption, integration, and uptake of the intervention using implementation outcomes, (c) the intervention’s effectiveness For improving nursing in this pilot setting. Discussion We seek to test whether it is possible to deliver and assess a set of theory-driven interventions to improve the quality of nursing documentation using quality improvement and implementation science methods and frameworks in a single facility in Sierra Leone. The results of this study will inform the design of a large-scale effectiveness-implementation study for improving nursing documentation practices for patients throughout hospitals in Sierra Leone. Trial registration Protocol version number 6, date: 24.12.2020, recruitment is planned to begin: January 2021, recruitment will be completed: December 2021.

This study aimed to develop a mapping table that connects nursing notes with standard terminology, focusing on nurses' concerns for ICU patients. After extracting nursing notes from a publicly accessible database, a research team, including a nursing informatics professor and researchers with ICU experience, developed a mapping table through a four-step process: initially reviewing literature on nurses' concerns, then extracting nursing notes from MIMIC IV and filtering the duplicate notes, subsequently defining and coding these concerns, and finally mapping them according to the CCC. Of 11,430,637 unstructured nursing notes from MIMIC IV, 265 unique notes remained after deduplication, with 208 notes reflecting nurses' concerns and categorized into 15 groups aligned with CCC. This mapping table will be a fundamental tool for predicting clinical deterioration in ICU patients by identifying important lexicons through natural language processing. [ABSTRACT FROM AUTHOR]

Objective: To design, create and validate an evaluation tool to measure progress of the patient within the national forensic mental health service. Methods: A methodological study with two sequential stages was used for this study. Stage 1 was the instrument development; stage 2 was expert judgment and each for these stages had 3 steps. Results: The 28-item questionnaire was submitted to 20 experts. Both descriptive and quantitative analysis were undertaken. The descriptive analysis included item ambiguity, median and percentage agreement. The quantitative method included a content validity index, content validity ratio and content validity coefficient. The acceptable values for item ambiguity, median and percentage agreement, content validity index, content validity ratio and content validity coefficient were a range of 3 or more between scores, median of 2.75 and above, 80 percent criterion, 0.79, 0.75 and 0.79 respectively. Conclusion: The 28-item tool met all the set criteria for content validity meeting the parameters established in the literature. [ABSTRACT FROM AUTHOR]

We aimed to create and validate a natural language processing algorithm to extract wound infection‐related information from nursing notes. We also estimated wound infection prevalence in homecare settings and described related patient characteristics. In this retrospective cohort study, a natural language processing algorithm was developed and validated against a gold standard testing set. Cases with wound infection were identified using the algorithm and linked to Outcome and Assessment Information Set data to identify related patient characteristics. The final version of the natural language processing vocabulary contained 3914 terms and expressions related to the presence of wound infection. The natural language processing algorithm achieved overall good performance (F‐measure = 0.88). The presence of wound infection was documented for 1.03% (n = 602) of patients without wounds, for 5.95% (n = 3232) of patients with wounds, and 19.19% (n = 152) of patients with wound‐related hospitalisation or emergency department visits. Diabetes, peripheral vascular disease, and skin ulcer were significantly associated with wound infection among homecare patients. Our findings suggest that nurses frequently document wound infection‐related information. The use of natural language processing demonstrated that valuable information can be extracted from nursing notes which can be used to improve our understanding of the care needs of people receiving homecare. By linking findings from clinical nursing notes with additional structured data, we can analyse related patients' characteristics and use them to develop a tailored intervention that may potentially lead to reduced wound infection‐related hospitalizations. [ABSTRACT FROM AUTHOR]

Background: There is an urgent need to improve quality of care to reduce avoidable mortality and morbidity from surgical diseases in low- and middle-income countries. Currently, there is a lack of knowledge about how evidence-based health system strengthening interventions can be implemented effectively to improve quality of care in these settings. To address this gap, we have developed a multifaceted quality improvement intervention to improve nursing documentation in a low-income country hospital setting. The aim of this pilot project is to test the intervention within the surgical department of a national referral hospital in Freetown, Sierra Leone. Methods: This project was co-developed and co-designed by in-country stakeholders and UK-based researchers, after a multiple-methodology assessment of needs (qualitative, quantitative), guided by a participatory 'Theory of Change' process. It has a mixed-method, quasi-experimental evaluation design underpinned by implementation and improvement science theoretical approaches. It consists of three distinct phases—(1) pre-implementation(project set up and review of hospital relevant policies and forms), (2) intervention implementation (awareness drive, training package, audit and feedback), and (3) evaluation of (a) the feasibility of delivering the intervention and capturing implementation and process outcomes, (b) the impact of implementation strategies on the adoption, integration, and uptake of the intervention using implementation outcomes, (c) the intervention's effectiveness For improving nursing in this pilot setting. Discussion: We seek to test whether it is possible to deliver and assess a set of theory-driven interventions to improve the quality of nursing documentation using quality improvement and implementation science methods and frameworks in a single facility in Sierra Leone. The results of this study will inform the design of a large-scale effectiveness-implementation study for improving nursing documentation practices for patients throughout hospitals in Sierra Leone. Trial registration: Protocol version number 6, date: 24.12.2020, recruitment is planned to begin: January 2021, recruitment will be completed: December 2021. [ABSTRACT FROM AUTHOR]

This study examined the effects of language differences between Korean and English on the performance of natural language processing in the classification task of identifying inpatient falls from unstructured nursing notes.

This study examined the effects of language differences between Korean and English on the performance of natural language processing in the classification task of identifying inpatient falls from unstructured nursing notes. [ABSTRACT FROM AUTHOR]

Nursing staff record observations about older people under their care in free-text nursing notes. These notes contain older people's care needs, disease symptoms, frequency of symptom occurrence, nursing actions, etc. Therefore, it is vital to develop a technique to uncover important data from these notes. This study developed and evaluated a deep learning and transfer learning-based named entity recognition (NER) model for extracting symptoms of agitation in dementia from the nursing notes. We employed a Clinical BioBERT model for word embedding. Then we applied bidirectional long-short-term memory (BiLSTM) and conditional random field (CRF) models for NER on nursing notes from Australian residential aged care facilities. The proposed NER model achieves satisfactory performance in extracting symptoms of agitation in dementia with a 75% F1 score and 78% accuracy. We will further develop machine learning models to recommend the optimal nursing actions to manage agitation.

This qualitative, descriptive, retrospective research aimed to describe how Nursing manages pain in children with cancer. The data were collected from the hospital notes of children hospitalised in a unit specialising in the treatment of cancer in a teaching hospital in South Brazil between May and June 2008. The quantitative data were submitted to descriptive analysis and the nursing notes were organised in a synoptic chart to which thematic analysis was applied. The results showed that 47.27% of children presented complaints of pain. Treatment with medicines was the principal response to all and any manifestations of crying; less invasive, or alternative strategies of pain management were rare. It was concluded that there is a need to establish methods for assessment and management of pain, according to the age group and level of development of the child, and to keep nursing notes with attention, allying technical-scientific knowledge with sensitivity and affection.

Background: Currently, the prediction values of models for the prognosis of acute kidney injury (AKI) receiving continuous renal replacement therapy (CRRT) were ordinary and establishing a better prediction model is necessary. Nursing notes are an important predictor of in-hospital mortality in intensive care unit (ICU) patients. This study established prognostic prediction models for AKI patients receiving CRRT especially using nursing notes., Methods: Totally, 682 AKI patients undergoing CRRT were included. AKI was diagnosed based on Kidney Disease: Improving Global Outcomes (KDIGO) criteria. Four hundred and twelve patients lacking nursing notes data were excluded. Finally, 270 patients were included and randomly divided into a training set (n=189) and a testing set (n=81) at a ratio of 7:3. Univariate analysis explored the possible predictors of mortality in AKI patients receiving CRRT. Random forest models and broad learning system (BLS) models (with or without sentiment scores) were respectively constructed in the training set and verified in the testing set. The performances of the models were assessed by the sensitivity, specificity, and area under the curve (AUC)., Results: For the random forest model including the sentiment scores, the AUC was 0.86 (95% CI: 0.81-0.91), the sensitivity was 0.72 (95% CI: 0.63-0.80), and the specificity was 0.87 (95% CI: 0.80-0.94) in the training set and the AUC was 0.78 (95% CI: 0.68-0.88), the sensitivity was 0.65 (95% CI: 0.49-0.80), and the specificity was 0.75 (95% CI: 0.62-0.88) in the testing set. For the BLS model including the sentiment scores, the AUC was 0.87 (95% CI: 0.82-0.92), the sensitivity was 0.95 (95% CI: 0.91-0.99) and the specificity was 0.48 (95% CI: 0.38-0.59) in the training set and the AUC was 0.82 (95% CI: 0.73-0.91), the sensitivity was 0.41 (95% CI: 0.25-0.56) and the specificity was 0.98 (95% CI: 0.93-1.00) in the testing set., Conclusions: The BLS models including the sentiment scores might offer a tool for quickly identifying patients AKI patients receiving CRRT with high risk of mortality and providing timely interventions to them for improving their prognosis., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://atm.amegroups.com/article/view/10.21037/atm-22-4403/coif). The authors have no conflicts of interest to declare., (2022 Annals of Translational Medicine. All rights reserved.)

This study analyzed what nurses wrote in narrative nursing notes for nursing outcome of cardiac-surgery patients. The nursing notes of 46 patients were decomposed into phrases and analyzed based on the nursing process. Eight patterns were extracted according to different combinations of nursing-process components, of which 29.2% have nursing outcome phrases. The content of the nursing notes was also classified into 15 categories, of which nursing outcomes were recorded more frequently in nursing care driven mainly by physician's order, such as disease-related symptom management, insomnia care, respiratory care, and pain control, than in independent nursing care such as education and emotional care. A survey on the attitudes of nurses toward the nursing record revealed that they do not document nursing outcomes as much as they think they do. The main reasons for this discrepancy were insufficient time for recording and lack of knowledge about why, how, and what to evaluate. Even though there is room for improvement, nursing notes represent a useful resource for determining nursing contributions to patient outcomes. [ABSTRACT FROM AUTHOR]

This study investigated the human-computer interfaces used for entering narrative nursing notes in the electronic medical record systems at six Korean hospitals. Using a criteria-based evaluation tool consisting of 17 elements revealed scores of 3.5-6.5. This implies that many criteria were not fulfilled and that considerable improvement is needed. [ABSTRACT FROM AUTHOR]

This study investigated the human-computer interfaces used for entering narrative nursing notes in the electronic medical record systems at six Korean hospitals. Using a criteria-based evaluation tool consisting of 17 elements revealed scores of 3.5-6.5. This implies that many criteria were not fulfilled and that considerable improvement is needed.

Background: Standardizing nursing handoffs at shift change is recommended to improve communication, with electronic tools as the primary approach. However, nurses continue to rely on personally created paper-based cognitive artifacts - their "paper brains" - to support handoffs, indicating a deficiency in available electronic versions., Objective: The purpose of this qualitative study was to develop a deep understanding of nurses' paper-based cognitive artifacts in the context of a cancer specialty hospital., Methods: After completing 73 hours of hospital unit field observations, 13 medical oncology nurses were purposively sampled, shadowed for a single shift and interviewed using a semi-structured technique. An interpretive descriptive study design guided analysis of the data corpus of field notes, transcribed interviews, images of nurses' paper-based cognitive artifacts, and analytic memos., Results: Findings suggest nurses' paper brains are personal, dynamic, living objects that undergo a life cycle during each shift and evolve over the course of a nurse's career. The life cycle has four phases: Creation, Application, Reproduction, and Destruction. Evolution in a nurse's individually styled, paper brain is triggered by a change in the nurse's environment that reshapes cognitive needs. If a paper brain no longer provides cognitive support in the new environment, it is modified into (adapted) or abandoned (made extinct) for a different format that will provide the necessary support., Conclusions: The "hidden lives" - the life cycle and evolution - of paper brains have implications for the design of successful electronic tools to support nursing practice, including handoff. Nurses' paper brains provide cognitive support beyond the context of handoff. Information retrieval during handoff is undoubtedly an important function of nurses' paper brains, but tools designed to standardize handoff communication without accounting for cognitive needs during all phases of the paper brain life cycle or the ability to evolve with changes to those cognitive needs will be underutilized., Competing Interests: The authors declare that they have no conflicts of interest in the research.

The ENR System of Seoul National University Bundang Hospital was made after analyzing paper-based narrative nursing records with ICNP, a combinatorial nursing terminology. In this study, we analyzed paper-based narrative nursing records with ICNP on surgical patients and evaluated practical use of the terminology and the system after building and applying ENR System. We found that we need to add new concepts to the ICNP to improve expression of nursing records especially in describing nursing actions. [ABSTRACT FROM AUTHOR]